© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198044
    Prev
    Next
    INDEX
    Explanations

    gang

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yao
    0.81
    yao
    0.64
    姚
    0.64
    Ya
    0.57
     Ya
    0.57
     ヤ
    0.55
    ヤ
    0.54
     Я
    0.53
    雅
    0.52
     야
    0.51
    POSITIVE LOGITS
     Muir
    0.57
     Gang
    0.53
    gang
    0.50
     gang
    0.49
    Gang
    0.46
     mu
    0.44
     му
    0.44
    gång
    0.42
     MU
    0.42
     gangs
    0.42
    Activations Density 0.023%

    No Known Activations